Systems and Methods Related to Controlling Autonomous Vehicle(s)

3. The method of claim 2, wherein the one or more additional ML layers of one or more of the trained ML models correspond to one of a plurality of disparate deciders, and wherein the further output comprises a decision made by each decider, of the plurality of disparate deciders, for each of the plurality of streams and with respect to each of the plurality of actors.

7. The method of claim 1, wherein the one or more predicted outputs include an autonomous vehicle control strategy or autonomous vehicle control commands, and wherein causing the autonomous vehicle to be controlled based on the one or more predicted outputs comprises causing the autonomous vehicle to be controlled based on the autonomous vehicle control strategy or autonomous vehicle control commands.

8. The method of claim 7, wherein the autonomous vehicle control strategy includes at least one of: a yield strategy, a merge strategy, a turning strategy, a traffic light strategy, an accelerating strategy, a decelerating strategy, or a constant velocity strategy.

9. The method of claim 7, wherein the autonomous vehicle control commands include a magnitude corresponding to at least one of: a velocity component, an acceleration component, or a steering component.

18. The method of claim 17, wherein the one or more predicted autonomous vehicle constraints that increase the cost of future motion of the autonomous vehicle or that restrict the future motion of the autonomous vehicle include one or more of: one or more locational constraints that restrict where the autonomous vehicle can be located in the environment, or one or more temporal constraints that restrict when the autonomous vehicle can perform the future motion in the environment.

19. The method of claim 1, wherein a quantity of the plurality of iterations is a fixed integer.

20. The method of claim 1, wherein a quantity of the plurality of iterations is dynamic.

22. The method of claim 1, wherein the one or more of the ML layers are ML layers of a transformer ML model or graph neural network ML model that include at least one or more attention function layers that are attentioned to one or more streams of the plurality of streams.

24. The method of claim 23, wherein, for a first iteration, of the plurality of iterations, each of the plurality of streams are designated as being one or more of: the target stream, the joining stream, the crossing stream, the adjacent stream, the additional stream, or the null stream.

25. The method of claim 24, wherein, for a second iteration, of the plurality of iterations, and subsequent to the second iteration, the designations for one or more of the plurality of streams are updated based on the updated trajectories.

26. The method of claim 1, wherein each of the corresponding additional actors associated with the plurality of actors correspond to one of: an additional vehicle that is in addition to the autonomous vehicle, a bicyclist, or a pedestrian.

27. The method of claim 1, wherein processing the trajectories for the autonomous vehicle and for each of the plurality of actors to forecast each of the trajectories with respect to each stream of the plurality of streams using the stream connection function causes a frame of reference of each of the trajectories to be shifted to one or more additional frames of reference of the other trajectories.